Biology subjects

Hughes, D. P.

Publications and source records attributed to Hughes, D. P..

7 recordsLinked to original sources

bioRxiv2026

Integrated Molecular and AI-Based Diagnostics for Banana Diseases: Development, Optimization, and Field Deployment of LAMP and Computer Vision Technologies

Banana and plantain (Musa spp.) production in Sub-Saharan Africa is severely constrained by multiple diseases, with Banana bunchy top virus (BBTV) representing the most devastating viral threat. Inadequate diagnostic infrastructure limits effective management, particularly for asymptomatic infections disseminated through informal planting material exchange. This study presents an integrated diagnostic framework combining Loop-Mediated Isothermal Amplification (LAMP) molecular diagnostics with deep learning-based computer vision for rapid, scalable disease detection under field conditions. A LAMP assay targeting the BBTV DNA-S coat protein gene was developed using conserved sequences from diverse African isolates and validated with a simplified alkaline extraction protocol eliminating conventional DNA purification. The assay achieved 100% specificity and concordant detection with PCR and qPCR, reducing diagnostic time from 4 to 6 hours to 60 minutes. In-house recombinant Bst LF polymerase production demonstrated comparable enzymatic performance to commercial alternatives, with projected per-reaction cost reductions of 70 to 80%. Concurrently, an SSDLite MobileNetV2 object detection model was developed through 19 iterative training cycles on 19,914 field-collected images spanning 22 disease and physiological stress classes. The final model achieved recall rates of 92.5% for BBTV, 91.0% for Banana Xanthomonas Wilt, and 98.1% for healthy leaf classification, deployed via the PlantVillage mobile application for real-time offline diagnostics. A QR code-based metadata system integrates phenotypic AI assessments with molecular confirmation for comprehensive surveillance. This complementary framework addresses broad-scale phenotypic screening and molecular confirmation of pre-symptomatic infections, providing accessible tools to safeguard food security across Sub-Saharan Africa.

plant biology↗

bioRxiv2023

A low-cost, AI-powered Measurement Verification and Reporting System for growing trees with smallholder farmers

Limited access to low-cost tools to measure, report, and verify (MRV) tree growth with smallholder farmers limits the scaling of tree planting efforts in developing countries. Artificial Intelligence (AI) offers the potential for low-cost, reliable, and accessible measurement and verification tools to be developed for an MRV platform to scale tree planting efforts in developing countries. Here, we present an AI-powered non-contact tree diameter measurement and verification tool. We have developed an AI-powered algorithm that accurately estimates the diameter of a tree from an image of the tree with a reference object. This non-contact measurement method utilizes semantic segmentation and image processing techniques to analyze an image of the tree with the reference object. The performance of the proposed method was evaluated on 142 trees with tape-measured diameters at breast height ranging from 5 to 60 cm. A regression analysis between predicted and measured diameter values had an R2 and an RMSE of 0.97 and 2.23 cm, respectively. Thus, using a smartphone application, the non-contact method developed here can empower anyone to accurately measure and report tree growth by just taking pictures of the trees with the reference object. The images submitted with on-farm measurements serve as data for future verification operations using the AI-powered algorithm. With the reference object serving as a unique tree identifier, a trees survival and diameter measurements can be tracked over time. The MRV system described here, with the developed AI-powered non-contact tree diameter measurement and verification tool, can empower organizations to plant, grow, and monitor trees with anyone, including smallholder farmers.

ecology↗

bioRxiv2020

Evaluating the accuracy of a smartphone-based artificial intelligence system, PlantVillage Nuru, in identifying the viral diseases of cassava

Premise of the studyNuru is an artificial intelligence system for diagnosis of plant diseases and pests developed as a public good by PlantVillage (Penn State University), FAO, IITA and CIMMYT. It provides a simple, inexpensive and robust means of conducting in-field diagnosis without requiring internet connection and provides real-time results and advice. The present work evaluates the effectiveness of Nuru as an in-field diagnostic tool by comparing the diagnosis capability of Nuru to that of cassava experts (researchers trained on cassava pests and diseases), agricultural extension agents and farmers. MethodsThe diagnosis capability of Nuru and that of the assessed individuals was determined by inspecting cassava plants in-field and by using the cassava symptom recognition assessment tool (CaSRAT) to score images of cassava leaves. ResultsNurus accuracy for symptom recognition when using six leaves (74 - 88%, depending on the condition) was similar to that of experts, 1.5-times higher than agricultural extension agents and two-times higher than farmers. DiscussionThese findings suggests that Nuru can be an effective tool for in-field diagnosis of cassava diseases and has a potential of being a quick and cost-effective means of disseminating knowledge from researchers to agricultural extension agents and farmers.

plant biology↗

bioRxiv2018

Modeling the impact of ex-nido transmitted parasites on ant colony dynamics

Infectious disease outbreaks are a common constraint of group living organisms. Ants (Hymenoptera: Formicidae) live in large, dense colonies and are host to a diverse range of parasites and pathogens, facilitating the possibility of epidemic-induced collapse. However, the majority of parasites infecting ants require a period of development outside of the nest before they can transmit to their next ant host ( ex-nido transmission) and the impact of these parasites on colony dynamics is unknown. Here we develop a mathematical model to assess ant colony dynamics in the presence of such parasites. We find that under field-realistic model conditions, such parasites are unlikely to cause the epidemic collapse of mature ant colonies, unless colony birth rate drops below 0.2328 ants/day. The preponderance of ex-nido transmitting parasites infecting ants and their limited epidemiological impact on colony dynamics may partly explain why collapsed ant colonies are rarely, if ever, observed in natural populations.

ecology↗

bioRxiv2018

Computer vision and deep learning automates nocturnal rainforest ant tracking to provide insight into behavior and disease risk

Determining how ant colonies optimize foraging while mitigating disease risk provides insight into how the ants have achieved ecological success. Fungal infected cadavers surround the main foraging trails of the carpenter ant Camponotus rufipes, offering a system to study how foragers behave given the persistent occurrence of disease threats. Studies on social insect foraging behavior typically require many hours of human labor due to the high density of individuals. To overcome this, we developed deep learning based computer vision algorithms to track foraging ants, frame-by-frame, from video footage. We found foragers can be divided into behavioral categories based on how straight they walk across the trail. Eighty percent of ants walk directly across the trail, while 20% wander or circle when crossing the trail. Departure from the main trail encourages exploration of new areas and could enhance discovery of new food resources. Conversely, results from our agent-based model simulations suggest deviation from a straight path exposes foragers to more infectious fungal spores. Consistency in walking behavior may protect most ants from infection, while the foragers with increased exposure due to their mode of walking could be a sufficient number of new hosts to sustain disease in this environment.

animal behavior and cognition↗

bioRxiv2018

Pathogens, parasites, and parasitoids of ants: a synthesis of parasite biodiversity and epidemiological traits

1.Ants are among the most ecologically successful organisms on Earth, with a global distribution and diverse nesting and foraging ecologies. Ants are also social organisms, living in crowded, dense colonies that can range up to millions of individuals. Understanding the ecological success of the ants requires understanding how they have mitigated one of the major costs of social living-infection by parasitic organisms. Additionally, the ecological diversity of ants suggests that they may themselves harbor a diverse, and largely unknown, assemblage of parasites. As a first step, we need to know the taxonomic and functional diversity of the parasitic organisms infecting ants. To that end, we provide a comprehensive review of the parasitic organisms infecting ants by collecting all extant records. We synthesize major patterns in parasite ecology by categorizing how parasites encounter their ant hosts, whether they require host death as a developmental necessity, and how they transmit to future hosts.\n\nWe report 1,415 records of parasitic organisms infecting ants, the majority of which come from order Diptera (34.8%), phylum Fungi (25.6%), and order Hymenoptera (25.1%). Most parasitic organisms infecting ants are parasitoids (89.6%), requiring the death of their host as developmental necessity and most initially encounter their hosts in the extranidal environment (68.6%). Importantly, though most parasitic organisms infecting ants only need a single host to complete their life cycle (89.2%), the vast majority need to leave the nest before transmission to the next ant host can occur (88.3%), precluding ant-to-ant transmission within the nest. With respect to the host, we only found records for 9 out of 17 extant ant sub-families, and for 82 out of the currently recognized 334 ant genera. Though there is likely bias in the records reported, both host and parasite ecological traits and evolutionary histories underlie the pattern of ant-parasite association reported here. This work provides a foundation for future work that will begin to untangle the ecological drivers of ant-parasite relationships and the evolutionary implications thereof.

ecology↗

bioRxiv2017

Evidences for convergent evolution of host parasitic manipulation in response to environmental conditions

Environmental conditions exert strong selection on animal behavior. We tested the hypothesis that the altered behavior of hosts due to parasitic manipulation is also subject to selection imposed by changes in environmental conditions over time. Our model system is ants manipulated by parasitic fungi to bite onto vegetation. We analyzed the correlation between forest type (tropical vs. temperate) and biting substrate (leaf vs. twigs), the time required for the fungi to reach reproductive maturity, and the phylogenetic relationship among specimens from tropical and temperate forests in different parts of the globe. We show that the fungal development in temperate forest is longer than the period of time leaves are present and the ants are manipulated to bite twigs. When biting twigs, 90% of the we examined dead ants had their legs wrapped around twigs, which appears to provide better attachment to the plant. Ancestral state character reconstruction suggests that the leaf biting is the ancestral trait and that twig biting is a convergent trait in temperate regions of the globe. These three lines of evidence suggest that changes in environmental conditions have shaped the manipulative behavior of the host by its parasite.

evolutionary biology↗